A temporally adaptive classifier for multispectral imagery

Author

Wang, Jianqi ; Azimi-Sadjadi, Mahmood R. ; Reinke, Donald

Author_Institution

Dept. of Electr. & Comput. Eng., Colorado State Univ., Fort Collins, CO, USA

Volume

15

Issue

1

fYear

2004

Firstpage

159

Lastpage

165

Abstract

This paper presents a new temporally adaptive classification system for multispectral images. A spatial-temporal adaptation mechanism is devised to account for the changes in the feature space as a result of environmental variations. Classification based upon spatial features is performed using Bayesian framework or probabilistic neural networks (PNNs) while the temporal updating takes place using a spatial-temporal predictor. A simple iterative updating mechanism is also introduced for adjusting the parameters of these systems. The proposed methodology is used to develop a pixel-based cloud classification system. Experimental results on cloud classification from satellite imagery are provided to show the usefulness of this system.

Keywords

Bayes methods; image classification; iterative methods; remote sensing; Bayesian framework; Multispectral Imagery; Temporally Adaptive Classifier; environmental variations; iterative updating mechanism; pixel-based cloud classification system; probabilistic neural networks; satellite imagery; spatial-temporal adaptation mechanism; spatial-temporal predictor; Adaptive systems; Bayesian methods; Clouds; Land surface temperature; Meteorology; Multispectral imaging; Neural networks; Reflectivity; Satellites; Weather forecasting; Image Processing, Computer-Assisted; Time Factors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2003.820622

Filename

1263587